中文版 | English

在结果中检索

CASIA OpenIR
（本次检索基于用户作品认领结果）

浏览/检索结果: 共5条，第1-5条 帮助

限定条件            
已选(0)清除 条数/页：   排序方式：
Hybrid Autoregressive and Non-Autoregressive Transformer Models for Speech Recognition 期刊论文
IEEE SIGNAL PROCESSING LETTERS, 2022, 页码: 762-766
作者:  Zhengkun Tian;  Jiangyan Yi;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(934Kb)  |  收藏  |  浏览/下载：265/76  |  提交时间：2022/06/14
One In A Hundred: Selecting the Best Predicted Sequence from Numerous Candidates for Speech Recognition 会议论文
, Tokyo, Japan, 14-17 December 2021
作者:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(563Kb)  |  收藏  |  浏览/下载：168/39  |  提交时间：2022/06/14
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization 会议论文
, Brno, Czechia, 30 August – 3 September
作者:  Zhengkun Tian;  Jiangyan Yi;  Ye Bai;  Jianhua Tao;  Shuai Zhang;  Zhengqi Wen
Adobe PDF(839Kb)  |  收藏  |  浏览/下载：185/42  |  提交时间：2022/06/14
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT 期刊论文
IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 期号: 29, 页码: 1897 - 1911
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(1163Kb)  |  收藏  |  浏览/下载：178/50  |  提交时间：2021/06/25
端到端语音识别、迁移学习、知识蒸馏、老师-学生学习、BERT、非自回归语音识别  
Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition 会议论文
, shanghai, 2020
作者:  Ye Bai;  Jiangyan Yi;  Jianhua Tao;  Zhengkun Tian;  Zhengqi Wen;  Shuai Zhang
Adobe PDF(801Kb)  |  收藏  |  浏览/下载：115/30  |  提交时间：2021/06/25